Need help with Smooth_AP?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

166 Stars 24 Forks MIT License 31 Commits 7 Opened issues


code for the ECCV '20 paper "Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval"

Services available


Need anything else?

Contributors list

# 196,261
5 commits


code for the ECCV '20 paper "Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval"

The PyTorch implementation of the Smooth-AP loss function is found in src/

Training code and pre-trained weights coming soon...



  • Python 3.7.7
  • PyTorch 1.6.0
  • Cuda 10.1


This repository is used for training using Smooth-AP loss on the following datasets:

  • PKU Vehicle ID (obtained from this website - must email authors for download permission)
  • INaturalist (2018 version - obtained from this website

We are the first to use the large-scale INaturalist dataset for the task of image retreival. The dataset splits can be downloaded here: . Unpack the zip into the INaturalist dataset directory.

Training the model

training results for the Vehicle ID and Inaturalist datasets can be replicated using this repository. To train the model on the Vehicle ID dataset, you can run:

  • python --fclrmul 1 --bs 384


If you find this work useful, please consider citing:

  author       = "Andrew Brown and Weidi Xie and Vicky Kalogeiton and Andrew Zisserman ",
  title        = "Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval",
  booktitle    = "European Conference on Computer Vision (ECCV), 2020.",
  year         = "2020",

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.